© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 67767
    Prev
    Next
    INDEX
    Explanations

    health, healing, and nutrition

    np_acts-logits-general · gemini-2.5-flash-lite

    gut health and toxins

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     statunitense
    0.43
    तीय
    0.41
     стороны
    0.41
    ким
    0.40
     rn
    0.40
     compañero
    0.39
    ക
    0.39
    合同
    0.38
     reinforcement
    0.38
     الاقوامی
    0.38
    POSITIVE LOGITS
     Detox
    0.63
     Toxicity
    0.62
     probiotic
    0.61
     detox
    0.60
     toxin
    0.60
     toxins
    0.59
     toxicity
    0.58
     biochem
    0.58
     microbiome
    0.57
     Biochem
    0.57
    Activations Density 0.304%

    No Known Activations